Unifying Perception and Action: A Hybrid-Modality Pipeline with Implicit Visual Chain-of-Thought for Robotic Action Generation

Documents similaires

• Temporal-Visual Semantic Alignment: A Unified Architecture for Transferring Spatial Priors from Vision Models to Zero-Shot Temporal Tasks
  par: Ma, Xiangkai, et autres
  Publié: (2025)
• A Wave is Worth 100 Words: Investigating Cross-Domain Transferability in Time Series
  par: Ma, Xiangkai, et autres
  Publié: (2024)
• Energy-Aware Pattern Disentanglement: A Generalizable Pattern Assisted Architecture for Multi-task Time Series Analysis
  par: Ma, Xiangkai, et autres
  Publié: (2025)
• ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Models
  par: Zhong, Linqing, et autres
  Publié: (2026)
• HALO: A Unified Vision-Language-Action Model for Embodied Multimodal Chain-of-Thought Reasoning
  par: Shou, Quanxin, et autres
  Publié: (2026)